Re:Science fails to face the shortcomings of statistics
by joe_the_user on Wednesday March 17, 2010 @08:40PM
(#1200137)
Actually, not even this is not true!
The Central Limit Theorem applies only to samples which have finite mean and variance (see: http://en.wikipedia.org/wiki/Central_limit_theorem).
Take a distribution which has infinite variance or mean and you can wind-up instead with one of the fractal distributions which Mandlebrot studied.
see http://en.wikipedia.org/wiki/Stable_distribution
Distributions with infinite variance or mean are more common than one might imagine. Some might argue the stock market would qualify.
Yes, for an infinite number of samples. The rate at which is converges to a Gaussian, though, is strongly dependent on the distribution from which the measurements are drawn.